Workplace Operations · AI Agents · Internal Systems · San Francisco

I run workplace operations and build the systems that run them.

Senior Workplace Coordinator at Airtable, managing the 300-person San Francisco headquarters and supporting four global offices. I taught myself AI-agent development and turned my own team's busiest workflows into production automation: visitor management, badging, ticketing, and events. Along the way I won Airtable's company-wide builders prize.

See the work LinkedIn ↗
65%
fewer tickets needing a manual response after my in-house AI support agent
est. 15+ hrs/wk
coordinator time saved by my visitor automation fleet
1st place
Airtable's company-wide AirLoop Builder Prize (solo build)
4 offices
SF · NYC · Austin · London: events, systems, and operations
$300K
annual flagship-events portfolio I plan and deliver

// selected work

Systems I've built

Every project below started as a manual workflow I personally ran, then rebuilt as software. Status labels are honest: Live means running in production today; Pre-launch and Prototype mean exactly that.

In-house AI support agent

Live

Workplace tickets were answered by hand, one at a time. I first deployed and trained a vendor AI help desk, learned its limits, then built our own in-house agent grounded in the company's Atlassian knowledge base, so answers come from our real documentation instead of guesses.

65% fewer tickets needing a manual response.
ai agentsatlassian kbragslack

Workplace ticketing system

Live

Requests arrived scattered across Slack DMs, hallway asks, and email, untracked and unreportable. I built the team's ticketing system in Airtable with Slack and email intake, turning every request into a tracked, measurable queue. This is the system the AI agent now deflects tickets from.

One reportable queue for every workplace request, feeding deflection analytics.
airtableslack intakeemail intake

Badge & occupancy data platform

Live

Badge-access events lived in a vendor silo with no way to answer "who actually uses the office?" I architected a 17-table platform ingesting access-control webhooks with deduplication and idempotency safe under concurrent delivery, reconciled against the employee directory. A monitoring agent watches the pipeline and caught a silently dropped webhook in production.

477 badge events and 270 employee visits reconciled against a 972-record directory.
webhooksidempotency17 tablesmonitoring agent

Badge program rebuild

Live

The legacy badge-tracking base had drifted from reality: I measured 85% record drift and badges stranded with departed employees. I replaced 15 legacy automations with a self-correcting request/loan system and native approval interfaces.

30 stranded badges recovered; 15 legacy automations replaced with a self-correcting system.
airtableapproval flowsdata repair

Event program infrastructure

Live

Company events ran on tribal knowledge. I built the reusable machinery: a city-parameterized venue-outreach pipeline with reply tracking and no-double-email guards, an RSVP/check-in/feedback system with QR distribution and AI-summarized post-event ratings, and attendance analytics correlating 484 prior-year RSVPs against comms touchpoints.

Four-office event portfolio (picnics, holiday parties, 800-person all-hands) on repeatable rails.
rsvp + qrai summariesanalyticsoutreach pipeline

Vendor & COI system of record

Live

Vendor compliance lived in inboxes. I built an 8-table system tracking 22 vendors and 64 contacts across four sites: certificate-of-insurance expiry against per-building requirements, service agreements per office, and budget-variance formulas tied to procurement.

Expired COIs surfaced automatically on active vendors, before they became building-access problems.
airtablecoi trackingbudget variance

Recognition automation

Pre-launch

Work-anniversary recognition meant manual gift orders every week. I built an agent that handles it end-to-end, designed safety-first: stage-only purchasing, read-only scoped tokens, and PII-safe logging. Validated end-to-end on synthetic data; in pre-launch.

Hard safety guarantees: the agent cannot spend real money or leak personal data by construction.
ai agentsleast privilegesynthetic testing

Candidate hosting workflow

Prototype

Hosting onsite interview candidates took coordinated manual work across recruiting, calendars, and the visitor system. My working prototype chains recruiter intake into auto-created calendar invites with room booking, visitor invites with NDA delivery, and auditable minimal-PII confirmations. Phased rollout planned.

One intake form replaces a multi-team coordination chain.
calendar apivisitor platformminimal pii

Four-office picnic system

Live

Simultaneous summer picnics in four cities, ~150 guests per site. I built the RSVP system with dietary rollups and a live dashboard, contracted venues, and ran a 26-post communications kit against a structured posting calendar.

Four cities, one system: venue, RSVP, dietary, and comms in a single pipeline.
rsvp systemlive dashboardcomms calendar

// the operator side

I build these because I run the function

The systems above aren't side projects. They automate work I own, and that operator context is why they get adopted.

300-person HQ + four global offices

Manage in-office operations for Airtable's San Francisco headquarters; support NYC, Austin, and London remotely: building relationships, badge/access, and visitor programs.

Flagship events, end to end

Own the company's flagship internal events (picnics, holiday parties, hack/build days, and 800-person all-hands where I draft the exec decks, run AV, and have MC'd) on a ~$300K annual budget.

$1M+ vendor transitions

Led two company-wide food-program transitions (pantry and daily lunch, each a $1M+ annual contract) from vendor selection through multi-office rollout. Manage 8+ vendors day to day: performance, scopes of work, on/offboarding.

Built an office, trained my successor

Ran Airtable's Austin office end-to-end (65–100 people, 20+ hires onboarded monthly), then fully transitioned my successor and helped train the NYC coordinator remotely.

Culture Committee board

Founding Culture Ambassador, advanced to the company Culture Committee alongside the Director of Employee Experience and Chief People Officer: company-wide culture, the ambassador program, and six ERGs.

Self-taught builder

Taught myself Claude Code, OpenAI Codex, and AI-agent development, then applied them to the workflows I knew best. Operator first, builder because of it.

// approach

How I build

Automate what you personally run

Every system started as my own manual workflow. I don't guess at requirements. I've done the job the software replaces.

Safety before capability

Least-privilege tokens, stage-only spending, PII-safe logging, human approval where it matters. Agents earn autonomy; they don't start with it.

Verify, don't hope

Idempotent ingestion, verification before submission, and monitoring agents watching the pipelines; one caught a silently dropped webhook in production.

Honest status, always

Live means live. Pre-launch means pre-launch. The same discipline applies to metrics: estimates are labeled as estimates.